Genetic Optimization Techniques for Enhancing Web Attacks Classification in Machine Learning

EasyChair Preprint 11002

Abstract

Web-based applications are now the preferred ap- proach for delivering a variety of services via the Internet. As a result of the globalization of commerce, web applications have been growing quickly and becoming increasingly complicated. Such applications have a significant security vulnerability in the online environment since they were developed with little experience and without testing or validation. Web application vulnerability is an issue brought on by the way the program was created. Numerous attackers use this security vulnerability to take control of the program, modify the data, and steal the most crucial information. They may also access all internal, unauthorized items. In this study, we present a hybrid model that classifies website attacks as benign through the integration of four gradient machine learning algorithms: Boost (GB), Multi- Layer Perceptron (MLP), and Boost. The study employed opti- mization algorithms such as K Nearest Neighbor (KNN), Logistic Regression, and Genetic algorithm (GA) to extract the optimal parameter. The model underwent evaluation utilizing a data set from the Canadian Institute 2023 that contains various types of attacks on the Internet of Things. Among these algorithms, GB achieved the best accuracy, with accuracy scores of 95%, and a score of 94% and 95% for accuracy, recall and F1-score, respectively.

Keyphrases: Genetic Algorithm Optimization, machine learning, web applications, web attack, web vulnerability

@booklet{EasyChair:11002,
  author    = {Ameera Jaradat and Ahmad Nasayreh and Qais Al-Na'Amneh and Hasan Gharaibeh and Rabia Al Mamlook},
  title     = {Genetic Optimization Techniques for Enhancing Web Attacks Classification in Machine Learning},
  howpublished = {EasyChair Preprint 11002},
  year      = {EasyChair, 2023}}